Add monitoring replacement baseline

2026-05-17 11:22:38 +02:00
parent 0c308ff352
commit c95fa601f0
10 changed files with 490 additions and 5 deletions
@@ -0,0 +1,109 @@
+{
+  "uid": "homelab-containers-logs",
+  "title": "Homelab / Containers + Logs",
+  "tags": ["homelab", "cadvisor", "loki", "dozzle-replacement"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "templating": {
+    "list": [
+      {
+        "name": "service",
+        "label": "Service",
+        "type": "query",
+        "datasource": "Loki",
+        "query": "label_values(compose_service)",
+        "refresh": 1,
+        "includeAll": true,
+        "multi": true,
+        "allValue": ".+",
+        "current": {
+          "selected": true,
+          "text": "All",
+          "value": "$__all"
+        }
+      },
+      {
+        "name": "search",
+        "label": "Regex Match",
+        "type": "textbox",
+        "query": ".+",
+        "current": {
+          "selected": true,
+          "text": ".+",
+          "value": ".+"
+        }
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "timeseries",
+      "title": "Container CPU",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[5m]))",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "cores"}, "overrides": []}
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Container memory",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (name) (container_memory_working_set_bytes{name!=\"\"})",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "bytes"}, "overrides": []}
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Log error rate",
+      "datasource": "Loki",
+      "gridPos": {"h": 8, "w": 24, "x": 0, "y": 8},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (compose_service) (count_over_time({compose_service=~\"${service:regex}\", container=~\".+\"} |~ \"(?i)error|exception|panic|fatal|traceback|oom|killed\" [$__interval]))",
+          "legendFormat": "{{compose_service}}"
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "type": "logs",
+      "title": "Live logs",
+      "datasource": "Loki",
+      "gridPos": {"h": 14, "w": 24, "x": 0, "y": 16},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "{compose_service=~\"${service:regex}\", container=~\".+\"} |~ \"$search\""
+        }
+      ],
+      "options": {
+        "showLabels": false,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      }
+    }
+  ]
+}